Rainfall-based river flow prediction using NARX in Malaysia

Flood forecasting is one of the most important and demanding operational responsibilities carried out by meteorological services all over the world. This task is complicated in the field of meteorology because all decisions have to consider in the visage of physiographical uncertainty factors such as the land coverage and vegetation, type of soil and topology of the catchment area [1][2]. This paper shows that the Nonlinear Autoregressive Exogenous (NARX) model can successfully to model a flow of the rivers 24 hours in advance based on current rainfall rates.